Update app.py

app.py

@@ -14,20 +14,24 @@ model = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=MODEL_FILENAME))
 scaler = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=SCALER_FILENAME))
 
 def encode_categorical_columns(df):
-    label_encoder = LabelEncoder()
-    
-    # Create a copy of the DataFrame to avoid modifying the original
+    # Create a copy of the DataFrame
     df_encoded = df.copy()
     
-    # Convert binary yes/no to 1/0
-    binary_columns = ['Visited Parent', 'Visited College for Inquiry', 'Attended Any Event']
+    # Convert Yes/No to 1/0 for binary columns
+    binary_columns = ['Visited Parent', 'Visited College for Inquiry', 'Attended Any Event', 'College']
     for col in binary_columns:
-        df_encoded[col] = df_encoded[col].map({'Yes': 1, 'No': 0})
+        df_encoded[col] = df_encoded[col].map({'Yes': 1, 'No': 0}).astype(float)
     
     # Encode other categorical columns
     categorical_columns = ['Location', 'Course', 'Faculty', 'Source', 'Event', 'Presenter']
+    label_encoder = LabelEncoder()
     for col in categorical_columns:
-        df_encoded[col] = label_encoder.fit_transform(df_encoded[col])
+        df_encoded[col] = label_encoder.fit_transform(df_encoded[col]).astype(float)
+    
+    # Ensure numerical columns are float
+    numerical_columns = ['College Fee', 'GPA', 'Year']
+    for col in numerical_columns:
+        df_encoded[col] = df_encoded[col].astype(float)
     
     return df_encoded
 
@@ -44,9 +48,9 @@ def predict_performance(Location, Course, College, Faculty, Source, Event, Prese
         'Visited Parent': [Visited_Parent],
         'Visited College for Inquiry': [Visited_College_for_Inquiry],
         'Attended Any Event': [Attended_Any_Event],
-        'College Fee': [float(College_Fee)],  # Convert to float
-        'GPA': [float(GPA)],  # Convert to float
-        'Year': [float(Year)]  # Convert to float
+        'College Fee': [float(College_Fee)],
+        'GPA': [float(GPA)],
+        'Year': [float(Year)]
     }
     
     input_df = pd.DataFrame(input_data)
@@ -54,29 +58,27 @@ def predict_performance(Location, Course, College, Faculty, Source, Event, Prese
     print("\nInput DataFrame:")
     print(input_df)
     
-    # Encode categorical variables
+    # Encode all categorical variables
     encoded_df = encode_categorical_columns(input_df)
     
     print("\nEncoded DataFrame:")
     print(encoded_df)
     
-    # Normalize numerical features (College Fee and Year)
-    numerical_features = ['College Fee', 'Year']
-    encoded_df[numerical_features] = encoded_df[numerical_features].astype(float)
+    # Normalize numerical features
+    # College Fee normalization
+    encoded_df['College Fee'] = (encoded_df['College Fee'] - 1000000) / (1700000 - 1000000)
     
-    # Create min-max scaling manually for College Fee
-    college_fee_min, college_fee_max = 1000000, 1700000
-    encoded_df['College Fee'] = (encoded_df['College Fee'] - college_fee_min) / (college_fee_max - college_fee_min)
+    # Year normalization
+    encoded_df['Year'] = (encoded_df['Year'] - 2019) / (2025 - 2019)
     
-    # Create min-max scaling manually for Year
-    year_min, year_max = 2019, 2025
-    encoded_df['Year'] = (encoded_df['Year'] - year_min) / (year_max - year_min)
+    # GPA normalization
+    encoded_df['GPA'] = (encoded_df['GPA'] - 2.0) / (3.0 - 2.0)
     
-    print("\nScaled DataFrame:")
+    print("\nNormalized DataFrame:")
     print(encoded_df)
     
     # Make prediction
-    prediction = model.predict(encoded_df)[0]
+    prediction = model.predict(encoded_df.astype(float))[0]
     
     # Clip prediction between 0 and 1
     prediction = np.clip(prediction, 0, 1)
@@ -85,7 +87,6 @@ def predict_performance(Location, Course, College, Faculty, Source, Event, Prese
     
     return f"Chance of Admission: {prediction:.1f}"
 
-# Create Gradio interface
 # Create Gradio interface
 iface = gr.Interface(
     fn=predict_performance,
@@ -94,7 +95,7 @@ iface = gr.Interface(
         gr.Radio(["MSc IT & Applied Security", "BSc (Hons) Computing", "BSc (Hons) Computing with Artificial Intelligence", 
                  "BSc (Hons) Computer Networking & IT Security", "BSc (Hons) Multimedia Technologies", "MBA", 
                  "BA (Hons) Accounting & Finance", "BA (Hons) Business Administration"], label="Course"),
-        gr.Radio(["Yes", "No"], label="College"),  # Add appropriate options for College
+        gr.Radio(["Yes", "No"], label="College"),
         gr.Radio(["Science", "Management", "Humanities"], label="Faculty"),
         gr.Radio(["Event", "Facebook", "Instagram", "Offline", "Recommendation"], label="Source"),
         gr.Radio(["New Year", "Dashain", "Orientation", "Fresher's Party", "Holi Festival", "Welcome Ceremony"], 
@@ -112,8 +113,6 @@ iface = gr.Interface(
     description="Predict the chances of a student's admission based on various inputs."
 )
 
-
-
 # Run the app
 if __name__ == "__main__":
     iface.launch(share=True)